Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12914
    Prev
    Next
    INDEX
    Explanations

    programming terminology and code structure elements related to class definitions and types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code: class, struct, interface, enum

    np_acts-logits-general · gemini-2.0-flash

    public programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antMatchers
    -0.73
    richTextPanel
    -0.70
    InputTagHelper
    -0.69
     jsPsych
    -0.65
    contentLoaded
    -0.62
    ToListAsync
    -0.61
    CodeAttribute
    -0.61
    pyplot
    -0.58
     jLabel
    -0.58
    Hochspringen
    -0.58
    POSITIVE LOGITS
     interface
    0.98
    interface
    0.92
     class
    0.86
     enum
    0.81
    class
    0.75
    enum
    0.70
    struct
    0.70
     struct
    0.69
     abstract
    0.67
    sealed
    0.66
    Activations Density 0.188%

    No Known Activations